6 results about "Joint constraints" patented technology

This application discloses a robot control method, apparatus, device, and storage medium, relating to the field of artificial intelligence technology. The method includes: obtaining an estimated Jacobian matrix for the robot based on the robot's historical measured poses of its end effector and historical measured joint angles; constructing a quadratic programming equation for the robot based on the measured joint angles, measured poses, predicted pose sequences, desired pose sequences, predicted joint angular velocity sequences, predicted joint angle sequences, and the estimated Jacobian matrix at a target time; solving the quadratic programming equation to obtain the predicted joint angular velocities of the robot at the target time; and controlling the end effector to follow the desired pose at the target time based on the predicted joint angular velocities at the target time. This application can directly handle the robot's joint constraint problem and accurately execute pose following tasks for robots with unknown models, thereby improving the robot's control accuracy and versatility.

An animated character includes an appendage with joints. The animated character also includes a joint restraint device attached to the appendage. The joint restraint device includes a membrane defining an internal volume and particles disposed within the internal volume. Furthermore, the joint restraint device is configured to press the particles against each other in response to a vacuum pressure applied to the membrane to restrain joint movement.

This invention belongs to the field of robot safety control technology and discloses a method for safe motion planning of a dual-redundant robotic arm. A linear mapping relationship is established between the joint spatial velocities of the redundant robotic arm and the velocity of the end effector. End effector velocity constraints, safety distance constraints, and joint amplitude constraints are established, and a multi-objective joint constraint model is established by integrating a differential kinematics model with the three types of constraints. The optimal decision variables satisfy the Cartesian-Kuhn-Tucker conditions. The original expression of the Cartesian-Kuhn-Tucker conditions is clarified, and a nonlinear complementary function is introduced to reconstruct the Cartesian-Kuhn-Tucker conditions. Based on the improved Cartesian-Kuhn-Tucker conditions, a vector error function is defined, and an adaptive zeroing neural network is designed. The vector error function is iteratively solved using the adaptive zeroing neural network to obtain the optimal decision variables of the multi-objective joint constraint model. The optimal decision variables are then used as the joint motion control commands for the robotic arm and output, completing the robotic arm motion planning.

The application discloses a 3D digital human audio driving method and system fusing deterministic motion prior and semantic mask constraint, and a terminal, and the method comprises the following steps: inputting a video image frame and 3DMM parameters of a target person, establishing a reference model with semantic consistency through a reconstruction network, and extracting deterministic motion prior and reference Gaussian semantic prior; inputting audio driving features, eye action unit information and the reference model into an audio driving network together, predicting face deformation and prediction semantics of audio driving under the joint constraint of the deterministic motion prior and the reference Gaussian semantic prior, and obtaining an initial rendering result after motion alignment; generating skin masks, lip masks, oral cavity masks and boundary masks according to the initial rendering result, and inputting all the masks and the initial rendering result into a repair network together for fine repair, and outputting a high-fidelity talking digital human result. The application realizes structure integrity and highly realistic specific person audio driving video synthesis.

The present application relates to a kind of three degrees of freedom dexterous hand finger compliance control method, comprising the following steps: establishing three degrees of freedom finger structure model;Passive joint constraint model and finger end kinematics model are constructed;In cartesian space, the compliance control model is constructed, and the end desired position offset is generated;Compliance control model is discretized;Lightweight kinematics inverse solution strategy is used, and only two active joints of third phalanx, second phalanx are solved, and the end desired position offset is mapped into the expected angle of active joint;According to the expected angle of active joint, motor control instruction is generated, third phalanx, second phalanx are driven to move, and first phalanx is driven to move by mechanical linkage, and end compliance interaction is realized;Contact force acquisition, compliance calculation, kinematics inverse solution and joint control step are cyclically executed, and real-time closed-loop control is completed.The method realizes the accurate mapping of end force, end position and active joint angle, and has good adaptability, real-time and compliance.

This application discloses a humanoid robot motion control method with joint constraints of text and trajectory, belonging to the field of humanoid robot control technology. The method first obtains the text description and motion trajectory corresponding to the preset control action. Through motion synthesis with joint constraints of text and trajectory, a SMPL digital human pose sequence conforming to dual constraints is generated. An optimization strategy combining stochastic gradient descent and momentum methods is used to complete motion redirection, obtaining pose data adapted to the target humanoid robot. A teacher-student model is constructed based on a proximal policy optimization algorithm, using the redirected pose data as prior guidance. Policy distillation is performed through a dataset aggregation algorithm to train the motion control model. Finally, the model is deployed to the robot, and motion control is achieved using the joint target angles output by the model as driving signals. This application provides high-quality prior guidance through dual constraints, effectively improving the semantic consistency, trajectory accuracy, anthropomorphism, and scene robustness of humanoid robot motion, significantly reducing training costs, and possessing excellent engineering application value.